We aim to stay on top of cutting-edge research in AI Safety Evaluations and develop a thoughtful community of critical thinkers eager to apply their skills to AI Safety. Sign up to attend using the links in the Event link column in the Schedule table below. In addition to participating as an attendee, you can suggest a paper for us to cover or volunteer to present one.
** The group is sponsored by BlueDot Impact* and run independently.
Host: Andreas Turanski (linkedin)
Co-host(s): Nange Sam (linkedin)
<aside> <img src="/icons/info-alternate_gray.svg" alt="/icons/info-alternate_gray.svg" width="40px" />
New here? Check below and our guide “How to Eval” which includes how to get the most from the reading group and more!
</aside>
| Date | Event link (RSVP) | Presenter | Paper (w link) | Paper | Blog post, etc. |
|---|---|---|---|---|---|
| Sept. 29, 2026 | Event RSVP | Andreas Turanski | GPT-6 Astra's Reduced CoT Monitorability - Live paper reading & discussion | Reading Guide (w papers) | |
| Oct. 6, 2026 | Event RSVP | Nange Sam | TBD | Paper | |
| Oct. 13, 2026 | Event RSVP | TBD | Paper |
Scroll down for Past Presentations.
Attendance and Comms
Discussion Norms
Papers and Presenting